Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    INDEX
    Explanations

    phrases and terms related to the concept of "initial" or starting points in various contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ess
    -0.18
    esh
    -0.17
    iid
    -0.16
    ese
    -0.16
    774
    -0.15
    endl
    -0.15
    esi
    -0.14
    alle
    -0.14
    831
    -0.14
     Tale
    -0.14
    POSITIVE LOGITS
    mente
    0.25
    aneously
    0.22
    /original
    0.19
    ë¶ĢíĦ°
    0.18
    iltr
    0.18
     tiên
    0.18
    dehyde
    0.17
    ities
    0.17
    (initial
    0.16
    arily
    0.15
    Act Density 0.017%

    No Known Activations